↓Skip to main content
Matrix Alchemy @RenoCrypt

RenoCrypt! 🎉 ML and Engineering

Mixing the mystique of alchemy with the science of ML algorithms. Highlighting the enigmatic nature of mathematical matrices used in machine learning.
Thank You For All The Support -- Benji

Explore the to know more about me. If you like what you see, check out the project on BookShelf or my Futra powered by RenoCrypt and ALL the open-source software as well as free digital infrastructure.

Recent

YOLO and object detection
·1148 words
The YOLO series of object detectors prioritizes speed and simplicity by framing object detection as a single regression problem.
More on Policy Gradient
·477 words
Off-policy algorithms open doors to learning from past experiences, while Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO) ensures stable policy updates.
Q-learning
·860 words
Q-learning, a cornerstone of reinforcement learning, is the quest of an agent to master its environment by discerning the quality of its actions.
What is Deep Reinforcement Learning (RL)
·891 words
Deep Reinforcement Learning (RL) combines deep learning techniques with reinforcement learning to enable agents to learn optimal strategies from large volumes of complex data.
What is Policy Gradient
·742 words
Policy Gradient is a method in reinforcement learning where the policy is directly optimized by estimating the gradient of the expected reward concerning the policy parameters